Extended thinking

Resolving Claude Opus 4.6 Thinking Model API Errors: A Complete Analysis of Format Compatibility Issues Between /v1/messages and /v1/chat/completions

by
claude opus 4 6 thinking api messages vs chat completions compatibility guide en image 0 图示

Ever run into this situation: you're using the claude-opus-4-6-thinking model, and calls via /v1/chat/completions (OpenAI format) work perfectly fine, but when you switch to /v1/messages (Anthropic native format), you get the error content: Input should be a valid list? This seemingly counterintuitive phenomenon actually reveals a deep compatibility issue with the Thinking model across the … Read more

OpenAI Compatible Mode vs Claude Native Format: 7 Key Differences That Determine Which Access Method You Should Use

by
openai compatible vs claude native api format difference guide en image 0 图示

Author's Note: A detailed comparison of 7 key differences between OpenAI-compatible mode and the native Claude API format, including support for features like Prompt Caching, Extended Thinking, and tool calling, to help you choose the most suitable integration method. Using the OpenAI SDK to call Claude models by just changing the base_url seems convenient—but you … Read more